Zobrazeno 1 - 10
of 331
pro vyhledávání: '"I, Đan"'
Autor:
Melamed, I. Dan, Niraula, Nobal B.
The challenge stated in the title can be divided into two main problems. The first problem is to reliably mimic the way that users interact with user interfaces. The second problem is to build an instructible agent, i.e. one that can be taught to exe
Externí odkaz:
http://arxiv.org/abs/1607.00061
Autor:
Melamed, I. Dan, Wang, Wei
Designers of statistical machine translation (SMT) systems have begun to employ tree-structured translation models. Systems involving tree-structured translation models tend to be complex. This article aims to reduce the conceptual complexity of such
Externí odkaz:
http://arxiv.org/abs/cs/0407005
Autor:
Melamed, I. Dan, Resnik, Philip
Publikováno v:
Computers and the Humanities 34(1-2). Special issue on SENSEVAL. pp. 79-84
We present methods for evaluating human and automatic taggers that extend current practice in three ways. First, we show how to evaluate taggers that assign multiple tags to each test instance, even if they do not assign probabilities. Second, we sho
Externí odkaz:
http://arxiv.org/abs/cs/0008007
Autor:
Melamed, I. Dan
Parallel texts (bitexts) have properties that distinguish them from other kinds of parallel data. First, most words translate to only one other word. Second, bitext correspondence is noisy. This article presents methods for biasing statistical transl
Externí odkaz:
http://arxiv.org/abs/cmp-lg/9805006
Autor:
Melamed, I. Dan
Bilingual annotators were paid to link roughly sixteen thousand corresponding words between on-line versions of the Bible in modern French and modern English. These annotations are freely available to the research community from http://www.cis.upenn.
Externí odkaz:
http://arxiv.org/abs/cmp-lg/9805005
Autor:
Melamed, I. Dan
A model of co-occurrence in bitext is a boolean predicate that indicates whether a given pair of word tokens co-occur in corresponding regions of the bitext space. Co-occurrence is a precondition for the possibility that two tokens might be mutual tr
Externí odkaz:
http://arxiv.org/abs/cmp-lg/9805003
Autor:
Melamed, I. Dan
This annotation style guide was created by and for the Blinker project at the University of Pennsylvania. The Blinker project was so named after the ``bilingual linker'' GUI, which was created to enable bilingual annotators to ``link'' word tokens th
Externí odkaz:
http://arxiv.org/abs/cmp-lg/9805004
Autor:
Melamed, I. Dan
Publikováno v:
Proceedings of the 35th Conference of the Association for Computational Linguistics (ACL'97), Madrid, Spain, 1997.
Many multilingual NLP applications need to translate words between different languages, but cannot afford the computational expense of inducing or applying a full translation model. For these applications, we have designed a fast algorithm for estima
Externí odkaz:
http://arxiv.org/abs/cmp-lg/9706026
Autor:
Melamed, I. Dan
Publikováno v:
Proceedings of the 2nd Conference on Empirical Methods in Natural Language Processing (EMNLP'97), Providence, RI, 1997.
Automatic segmentation of text into minimal content-bearing units is an unsolved problem even for languages like English. Spaces between words offer an easy first approximation, but this approximation is not good enough for machine translation (MT),
Externí odkaz:
http://arxiv.org/abs/cmp-lg/9706027
Autor:
Melamed, I. Dan
Publikováno v:
Proceedings of the 35th Conference of the Association for Computational Linguistics (ACL'97), Madrid, Spain, 1997.
The first step in most empirical work in multilingual NLP is to construct maps of the correspondence between texts and their translations ({\bf bitext maps}). The Smooth Injective Map Recognizer (SIMR) algorithm presented here is a generic pattern re
Externí odkaz:
http://arxiv.org/abs/cmp-lg/9706025